Refiner connector for AI agents

Tools your feedback agent reaches for on Refiner, scoped per user.

CALL ANY TOOL

19 tools for user surveys in Refiner: list surveys and responses, read reporting, identify contacts and track events, tag responses, manage segment membership, and publish, duplicate, or archive surveys.

refiner_add_contact_to_segment

Add contact to segment

Add a user to a manual segment. Returns message, contact_uuid and segment_uuid. Creates the user if no match exists. Use refiner_list_segments to find manual segments. Use refiner_remove_contact_from_segment to undo.

Parameters

Name

Type

Required

Description

segment_uuid

string

Required

UUID of the manual segment. Example: 4f5637d0-3d0d-11ea-b965-614418dec30c

string

Optional

Email address of the contact; use when you have no user ID. Example: jane@awesome.com

string

Optional

Your own user ID for the contact, the same ID used with identify user. Example: user_123

refiner_archive_form

Archive form

refiner_delete_contact

Delete contact

refiner_duplicate_form

Duplicate form

refiner_get_account_info

Get account info

refiner_get_contact

Get contact

refiner_get_environment

Get environment

refiner_get_form_history

Get form history

refiner_get_reporting

Get reporting

refiner_identify_user

Identify user

refiner_list_contacts

List contacts

refiner_list_forms

List forms

refiner_list_responses

List responses

refiner_list_segments

List segments

refiner_publish_form

Publish form

refiner_remove_contact_from_segment

Remove contact from segment

refiner_store_response

Store response

refiner_tag_response

Tag response

refiner_track_event

Track event

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Refiner tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["refiner"], toolNames: [
    "refiner_list_forms",
    "refiner_list_responses",
    "refiner_get_reporting"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarize this month's NPS responses and the main detractor themes" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["refiner"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize this month's NPS responses and the main detractor themes" }],
  tools,
});

// Execute the tool call with the user's vaulted Refiner access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["refiner"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize this month's NPS responses and the main detractor themes" }],
  tools,
});

// Tool call runs with the user's vaulted Refiner access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["refiner"] }, pageSize: 100,
});

const agent = new Agent({
  name: "feedback_agent",
  model: "gemini-2.5-pro",
  instruction: "Refiner tools scoped to this user",
  tools,
});

await agent.run("Summarize this month's NPS responses and the main detractor themes");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Refiner tool. Click to copy, paste into your agent, done.

Responses

Copy the prompt

Copied

List the latest 20 responses to our NPS survey.

Copy the prompt

Copied

Show NPS reporting for the last 30 days.

Copy the prompt

Copied

Tag every response that mentions pricing with the tag pricing.

Surveys

Copy the prompt

Copied

List our published surveys.

Copy the prompt

Copied

Duplicate the Onboarding CSAT survey as a new draft.

Copy the prompt

Copied

Unpublish the Q3 feature survey.

Contacts and segments

Copy the prompt

Copied

Show everything Refiner has on jane@acme.com.

Copy the prompt

Copied

Add user 4821 to the Beta Testers segment.

Copy the prompt

Copied

Track a Completed Onboarding event for user 4821.

SEE HOW AUTH WORKS

Each user connects their own Refiner access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Refiner

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Refiner

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Refiner

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Refiner

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other customer feedback and analytics connectors.

Support and Ops Teams

Freshdesk CSAT agent

Watches Freshdesk for resolved tickets, emails each requester a CSAT survey from Gmail, and writes the score and the verbatim back onto the ticket, every call on the support rep's own delegated OAuth.

Freshdesk

Gmail

View agent

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Refiner access token looks fine in a demo. In production every survey change and contact update looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Refiner today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Refiner as the user or through a shared access token?

As the user. Each user connects their own Refiner access token once, and Scalekit sends it with every call. Audit logs attribute every survey change and contact update to that user, not a shared service account.

Where is the Refiner access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Refiner?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the survey, response, and reporting read tools without refiner_delete_contact, which permanently deletes a contact and their survey responses. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Refiner access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent send data into Refiner as well as read it?

Yes. refiner_identify_user creates or updates a contact with traits, refiner_track_event records a named event for a user, and refiner_store_response stores a survey response, for example to import historical data.